[PATCH v2][AArch64] Fix symbol offset limit

[Wilco Dijkstra]

  ping

From: Wilco Dijkstra
Sent: 12 September 2016 15:50
To: Richard Earnshaw; GCC Patches
Cc: nd
Subject: Re: [PATCH v2][AArch64] Fix symbol offset limit
    
Wilco wrote:    
> The original example is from GCC itself, the fixed_regs array is small but due to
> optimization we can end up with &fixed_regs + 0xffffffff.

We could also check the bounds of each symbol if they exist, like the patch below.


In aarch64_classify_symbol symbols are allowed full-range offsets on relocations.
This means the offset can use all of the +/-4GB offset, leaving no offset available
for the symbol itself.  This results in relocation overflow and link-time errors
for simple expressions like &global_char + 0xffffff00.

To avoid this, limit the offset to +/-1GB so that the symbol needs to be within a
3GB offset from its references.  For the tiny code model use a 64KB offset, allowing
most of the 1MB range for code/data between the symbol and its references.
For symbols with a defined size, limit the offset to be within the size of the symbol.

ChangeLog:
2016-09-12  Wilco Dijkstra  <wdijkstr@arm.com>

    gcc/
        * config/aarch64/aarch64.c (aarch64_classify_symbol):
        Apply reasonable limit to symbol offsets.

    testsuite/
        * gcc.target/aarch64/symbol-range.c (foo): Set new limit.
        * gcc.target/aarch64/symbol-range-tiny.c (foo): Likewise.

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 385bd560fb12cd5d404e6ddb2f01edf1fe72d729..275a828ac9e6e9b8187380c1b602ffb1b2bcfb21 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -9351,6 +9351,8 @@ aarch64_classify_symbol (rtx x, rtx offset)
       if (aarch64_tls_symbol_p (x))
         return aarch64_classify_tls_symbol (x);
 
+      const_tree decl = SYMBOL_REF_DECL (x);
+
       switch (aarch64_cmodel)
         {
         case AARCH64_CMODEL_TINY:
@@ -9359,25 +9361,45 @@ aarch64_classify_symbol (rtx x, rtx offset)
              we have no way of knowing the address of symbol at compile time
              so we can't accurately say if the distance between the PC and
              symbol + offset is outside the addressible range of +/-1M in the
-            TINY code model.  So we rely on images not being greater than
-            1M and cap the offset at 1M and anything beyond 1M will have to
-            be loaded using an alternative mechanism.  Furthermore if the
-            symbol is a weak reference to something that isn't known to
-            resolve to a symbol in this module, then force to memory.  */
+            TINY code model.  So we limit the maximum offset to +/-64KB and
+            assume the offset to the symbol is not larger than +/-(1M - 64KB).
+            Furthermore force to memory if the symbol is a weak reference to
+            something that doesn't resolve to a symbol in this module.  */
           if ((SYMBOL_REF_WEAK (x)
                && !aarch64_symbol_binds_local_p (x))
-             || INTVAL (offset) < -1048575 || INTVAL (offset) > 1048575)
+             || !IN_RANGE (INTVAL (offset), -0x10000, 0x10000))
             return SYMBOL_FORCE_TO_MEM;
+
+         /* Limit offset to within the size of a declaration if available.  */
+         if (decl && DECL_P (decl))
+           {
+             const_tree decl_size = DECL_SIZE (decl);
+
+             if (decl_size
+                 && !IN_RANGE (INTVAL (offset), 0, tree_to_shwi (decl_size)))
+               return SYMBOL_FORCE_TO_MEM;
+           }
+
           return SYMBOL_TINY_ABSOLUTE;
 
         case AARCH64_CMODEL_SMALL:
           /* Same reasoning as the tiny code model, but the offset cap here is
-            4G.  */
+            1G, allowing +/-3G for the offset to the symbol.  */
           if ((SYMBOL_REF_WEAK (x)
                && !aarch64_symbol_binds_local_p (x))
-             || !IN_RANGE (INTVAL (offset), HOST_WIDE_INT_C (-4294967263),
-                           HOST_WIDE_INT_C (4294967264)))
+             || !IN_RANGE (INTVAL (offset), -0x40000000, 0x40000000))
             return SYMBOL_FORCE_TO_MEM;
+
+         /* Limit offset to within the size of a declaration if available.  */
+         if (decl && DECL_P (decl))
+           {
+             const_tree decl_size = DECL_SIZE (decl);
+
+             if (decl_size
+                 && !IN_RANGE (INTVAL (offset), 0, tree_to_shwi (decl_size)))
+               return SYMBOL_FORCE_TO_MEM;
+           }
+
           return SYMBOL_SMALL_ABSOLUTE;
 
         case AARCH64_CMODEL_TINY_PIC:
diff --git a/gcc/testsuite/gcc.target/aarch64/symbol-range-tiny.c b/gcc/testsuite/gcc.target/aarch64/symbol-range-tiny.c
index d7e46b059e41f2672b3a1da5506fa8944e752e01..d399a3637ed834ddc4bb429594c4ec229b5c2ea8 100644
--- a/gcc/testsuite/gcc.target/aarch64/symbol-range-tiny.c
+++ b/gcc/testsuite/gcc.target/aarch64/symbol-range-tiny.c
@@ -1,12 +1,12 @@
-/* { dg-do compile } */
+/* { dg-do link } */
 /* { dg-options "-O3 -save-temps -mcmodel=tiny" } */
 
-int fixed_regs[0x00200000];
+char fixed_regs[0x00200000];
 
 int
-foo()
+main()
 {
-  return fixed_regs[0x00080000];
+  return fixed_regs[0x000ff000];
 }
 
 /* { dg-final { scan-assembler-not "adr\tx\[0-9\]+, fixed_regs\\\+" } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/symbol-range.c b/gcc/testsuite/gcc.target/aarch64/symbol-range.c
index 6574cf4310430b847e77ea56bf8f20ef312d53e4..4b4ec8dab9321026d1fae96d336565a7883c8203 100644
--- a/gcc/testsuite/gcc.target/aarch64/symbol-range.c
+++ b/gcc/testsuite/gcc.target/aarch64/symbol-range.c
@@ -1,12 +1,12 @@
-/* { dg-do compile } */
+/* { dg-do link } */
 /* { dg-options "-O3 -save-temps -mcmodel=small" } */
 
-int fixed_regs[0x200000000ULL];
+char fixed_regs[0x200000000ULL];
 
 int
-foo()
+main()
 {
-  return fixed_regs[0x100000000ULL];
+  return fixed_regs[0xfffff000ULL];
 }
 
 /* { dg-final { scan-assembler-not "adrp\tx\[0-9\]+, fixed_regs\\\+" } } */